CN111765593A - Air conditioner throttling component fault early warning method and air conditioner - Google Patents
Air conditioner throttling component fault early warning method and air conditioner Download PDFInfo
- Publication number
- CN111765593A CN111765593A CN202010647406.4A CN202010647406A CN111765593A CN 111765593 A CN111765593 A CN 111765593A CN 202010647406 A CN202010647406 A CN 202010647406A CN 111765593 A CN111765593 A CN 111765593A
- Authority
- CN
- China
- Prior art keywords
- fault
- air conditioner
- data
- early warning
- throttling element
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/32—Responding to malfunctions or emergencies
- F24F11/38—Failure diagnosis
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/52—Indication arrangements, e.g. displays
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
Landscapes
- Engineering & Computer Science (AREA)
- Combustion & Propulsion (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Signal Processing (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a fault early warning method for a throttling component of an air conditioner and the air conditioner, wherein operation data in a period of time before the fault of the air conditioner is acquired, the operation state of the throttling component is correspondingly marked on the operation data, and sample data is generated; constructing a model according to the sample data, and generating a fault prediction model; and acquiring the operating data of the air conditioner in real time, and predicting whether the air conditioner throttling element fails or not through the fault prediction model. The method aims to early warn the faults of the throttling components in advance, reduce the consumption of human resources and shorten the time for solving the faults.
Description
Technical Field
The invention relates to the technical field of air conditioners, in particular to an air conditioner throttling element fault early warning method and an air conditioner.
Background
The throttling element is used as an essential accessory of the variable frequency air conditioner, and the stable and efficient operation of the air conditioning system is ensured through electric signal control. Meanwhile, the function of a safety protector can be realized, the system performance and efficiency are higher, and the heat loss generated by starting and suspending of the air conditioner compressor can be reduced. However, when the throttling element is out of order, the use of the air conditioner is influenced. At present, air conditioner designers inquire data meeting conditions from monitoring software, manually compare the data after exporting Excel, and investigate whether running data has problems, so as to perform fault location and modify design schemes. The whole process consumes a great amount of manpower and time, and the problem solving time is prolonged.
Disclosure of Invention
The invention mainly aims to provide an air conditioner throttling element fault early warning method and an air conditioner, aiming at early warning the throttling element fault, reducing the consumption of human resources and shortening the time for solving the fault.
In order to achieve the purpose, the air conditioner throttling element fault early warning method provided by the invention is characterized in that operation data in a period of time before the air conditioner fault is acquired, the operation state of a throttling element is correspondingly marked on the operation data, and sample data is generated;
constructing a model according to the sample data, and generating a fault prediction model;
and acquiring the operating data of the air conditioner in real time, and predicting whether the air conditioner throttling element fails or not through the fault prediction model.
Preferably, the operation data of the air conditioner or the operation data of the air conditioner in a period before the fault at least includes: and the time interval is the compressor load corresponding to the time interval, the absolute value of the difference value of the water outlet temperature and the water inlet temperature, the exhaust pressure before the compressor is started, the suction pressure before the compressor is started, and the suction pressure after the compressor is started or the pressure of a pipe body at the exhaust end after the compressor is started.
Preferably, the fault prediction model is constructed by using an LSTM algorithm.
Preferably, the generating the fault prediction model specifically includes:
if the state mark of the throttling element is normal, inputting the preprocessed sample data corresponding to the state mark to a forgetting gate of an LSTM algorithm; if the state mark of the throttling element is a fault, inputting the preprocessed sample data corresponding to the state mark to an input gate of the LSTM algorithm to obtain an output gate of the LSTM algorithm; and
and repeating the previous judging step until all sample data are input, and obtaining a fault prediction model.
Preferably, the step of correspondingly marking the operating state of the throttling element on the operating data specifically includes: setting a numerical range of operation data in a period of time before the air conditioner fails when the state of the throttling element is in a fault state; and comparing the operation data in a period of time before the air conditioner fault with a set numerical range, and marking the state of the throttling element as a fault when the operation data in the period of time before the air conditioner fault falls into the numerical range when the state is the fault.
Preferably, the operation data further includes operating condition parameters, and the operating condition parameters are divided into cooling parameters and heating parameters.
Preferably, the operation data is preprocessed, and the preprocessing includes: and rejecting abnormal data, making up data loss and judging peak values.
Preferably, the making up for the data loss includes: at least one of mean interpolation, maximum likelihood estimation, and multiple interpolation.
Preferably, the sample data of the fault prediction model includes experimental data and/or historical operating data obtained after judgment of the associated fault under the laboratory condition.
In addition, the application also provides an air conditioner, which comprises a controller and a throttling element, wherein the controller carries out early warning data processing on the fault of the throttling element according to the air conditioner throttling element fault early warning method.
The air conditioner throttling element fault early warning method provided by the invention has the beneficial effects that: 1. the method comprises the steps of acquiring operation data of the air conditioner within a certain time in real time, predicting the operation state of the throttling component of the air conditioner, and making a fault early warning by a fault prediction model in advance when the operation of the throttling component of the air conditioner is about to be abnormal. The data comparison is not needed by designers one by one, and the working efficiency of workers is greatly improved. 2. Because the fault can be early warned in advance, manual comparison is not needed, and the consumption of human resources is reduced. 3. By pre-warning and predicting the generation of the fault, the preparation for coping can be made in advance, and the time for solving the fault is shortened.
Drawings
FIG. 1 is a schematic flow chart of a fault early warning method for an air conditioner throttling element according to the invention;
FIG. 2 is a first embodiment of a running data state flag;
FIG. 3 is a second embodiment of a running data state flag.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and examples. It should be understood that the following specific examples are only for illustrating the present invention and are not to be construed as limiting the present invention.
As shown in fig. 1, the invention provides a fault early warning method for an air conditioner throttling element, which comprises the following steps:
s100: acquiring operation data in a period of time before the air conditioner fault;
s200: correspondingly marking the operating state of the throttling element on the operating data to generate sample data;
s300: constructing a model according to the sample data, and generating a fault prediction model;
s400: and acquiring the operating data of the air conditioner in real time, and predicting whether the air conditioner throttling element fails or not through the fault prediction model.
Before acquiring data, different types of sensors are firstly installed on the air conditioner and used for detecting the operation data of each component of the air conditioner, wherein the sensors at least comprise a pressure sensor, a voltage sensor, a current sensor, a temperature sensor and the like. Of course other types of sensors may be used to obtain more operational data as required by the design.
In this embodiment, the data acquisition may be performed by a data acquisition server or other data acquisition terminals. In this embodiment, in order to meet the requirement of big data, the data acquisition server is used as the data acquisition terminal, the data acquisition server acquires the operation data acquired by different sensors on different air conditioners in the same time, the data acquisition server and the sensors transmit data in a GPRS (general packet radio service) communication mode, and the GPRS (general packet radio service) transmission mode is used, so that the transmission speed is high, the data volume is large, and a guarantee is provided for large-scale data transmission. Of course, data transmission can be performed in a manner of bluetooth or WIFI (a wireless network transmission technology) according to design requirements. Before the sensors of different types installed on the air conditioner communicate with the data acquisition server, authentication is needed to be carried out firstly, data leakage is avoided, data safety is guaranteed, and then transmitted data are encrypted in the data transmission process, so that data safety is further guaranteed. The specific encryption mode can be the encryption mode commonly used in the prior art.
And after the decryption is completed, the data acquisition server analyzes the data to acquire the numerical values of the operation data of each part of the air conditioner.
In this embodiment, the storage module adopts a Hadoop (distributed system infrastructure) cluster storage server, wherein a Hadoop cluster is composed of 7 servers, 2 of which are used as management nodes for realizing data processing, specifically including software management, configuration management, fault management, performance management, security management, tenant management, backup management, and the like; and the other 5 stations are used as storage nodes for storing the operation data. The distributed storage management system is built on the Hadoop cluster and comprises an HDFS distributed file system, a NoSQL database, a Solr search engine, an SQL storage format and the like. By adopting the technical scheme, the safety of data storage can be ensured, and meanwhile, the data storage device has better throughput capacity when facing large data volume.
Marking the operation data, comparing the operation data with a preset logic according to the acquired operation data, judging whether the air conditioner is in failure or not, and marking the air conditioner throttling element as normal when the operation data does not meet the preset logic; and when the operation data meet the preset logic, marking the air conditioner throttling element as a fault. And binding the marking result with the corresponding operation data so as to finish the data marking, and recording the marked operation data as sample data.
The fault prediction model obtains the operation data of the air conditioner, predicts whether the throttling element of the air conditioner fails or not, and pushes the failure information to the control terminal of the storage server. The control terminal may be a portable mobile device, a PC, or the like.
By adopting the technical scheme, the operation data of the air conditioner within a certain time is acquired in real time, the operation state of the throttling component of the air conditioner is predicted, and when the operation of the throttling component of the air conditioner is about to be abnormal, the fault prediction model gives a fault early warning in advance. The data comparison is not needed by designers one by one, and the working efficiency of workers is greatly improved. Meanwhile, the system can early warn the generation of faults in advance, manual comparison is not needed, and the consumption of human resources is reduced. The system can predict the generation of the fault in advance through early warning, prepare for responding in advance and shorten the time for solving the fault.
Preferably, the operation data of the air conditioner or the operation data of the air conditioner in a period before the fault at least includes: and the time interval is the compressor load corresponding to the time interval, the absolute value of the difference value of the water outlet temperature and the water inlet temperature, the exhaust pressure before the compressor is started, the suction pressure before the compressor is started, and the suction pressure after the compressor is started or the pressure of a pipe body at the exhaust end after the compressor is started.
The operation state of the air conditioner in the time interval can be obtained through the operation data, the fault prediction model is accurately judged according to the relation among the operation data, and the judgment precision of the fault prediction model is improved.
Preferably, the fault prediction model is constructed by using an LSTM algorithm.
In particular, LSTM refers to a long-short term memory network, in this embodiment, byZero clearing functionGenerating an all-zero initial state, defining a loss function, transmitting the current input and the state of the air conditioner throttling element at the previous moment into a defined LSTM structure, obtaining the output and the updated state of the current LSTM structure, transmitting the output of the current LSTM structure into a full connection layer, obtaining the final output, and calculating the loss of the output at the current moment. And pre-judging whether the air conditioner throttling element fails in advance by acquiring the final loss, so that the early warning of the throttling element is realized.
Preferably, the generating the fault prediction model specifically includes:
if the state mark of the throttling element is normal, inputting the preprocessed sample data corresponding to the state mark to a forgetting gate of an LSTM algorithm; if the state mark of the throttling element is a fault, inputting the preprocessed sample data corresponding to the state mark to an input gate of the LSTM algorithm to obtain an output gate of the LSTM algorithm; and
and repeating the previous judging step until all sample data are input, and obtaining a fault prediction model.
Specifically, the state of the throttling element in the sample data is obtained, and when the state of the throttling element is normal, the state is input into a forgetting gate of an LSTM algorithm, and the main line is forgotten. When the state of the throttling element is a fault, the fault state is input into the main line through the input gate, the output gate of the LSTM is obtained, the loss function at the current moment is calculated, and whether the air conditioner throttling element has the fault or not is judged in advance.
Preferably, the step of correspondingly marking the operating state of the throttling element on the operating data specifically includes: setting a numerical range of operation data in a period of time before the air conditioner fails when the state of the throttling element is in a fault state; and comparing the operation data in a period of time before the air conditioner fault with a set numerical range, and marking the state of the throttling element as a fault when the operation data in the period of time before the air conditioner fault falls into the numerical range when the state is the fault.
Specifically, the load of the compressor is FU, the absolute value of the difference between the temperature of the outlet water and the temperature of the inlet water is WEN, and the high-pressure parameter of the exhaust gas before the compressor is started is GAO;
as shown in fig. 2 and 3, firstly, judging whether the compressor load FU meets FU of 0% to 50%, and when the compressor load FU meets the condition, continuously judging whether the absolute value WEN of the inlet water temperature difference meets WEN of 5 ℃; when the absolute value WEN of the inlet water temperature difference value meets the condition, continuously judging whether the exhaust high-pressure parameter GAO before the compressor is started meets GAO & gt 260 Kpa; and when all the parameters meet the conditions, the fault prediction model outputs the fault of the throttling element and feeds the result back to the control end of the storage server. Of course, the threshold may be fine-tuned according to design requirements.
It can be understood that the load after the compressor is started is between 0% and FU less than or equal to 50%, namely the compressor is abnormally operated, and the reason for the abnormal operation of the compressor can be shown as follows: 1. the compressor itself fails; 2. a throttling component failure, etc. Meanwhile, when the absolute value WEN of the inlet water temperature difference satisfies that the absolute value WEN of the inlet water temperature difference is less than or equal to 5 ℃, the temperature difference of inlet and outlet water is small, and the condition may occur that: 1. a throttling component failure; 2. the condensate valve is not open, etc. Similarly, when the high-pressure parameter of exhaust before the compressor is started, the low-pressure parameter of suction of the compressor and the pressure parameter of the pipe body at the exhaust end after the compressor is started are all abnormal, the fault of the throttling element can be uniquely deduced.
The low suction pressure before the compressor is started is defined as QD, and the low suction pressure after the compressor is started is defined as HD.
When the compressor load FU, the absolute value WEN of the inlet water temperature difference value and the exhaust high-pressure parameter GAO before the compressor is started meet the threshold condition, judging whether the suction low-pressure QD before the compressor is started meets QD & gt 260 Kpa; and when the QD meets the QD more than 260Kpa before the compressor is started, continuously judging whether any one of the suction low-pressure parameter after the compressor is started or the pressure parameter of the exhaust end pipe body after the compressor is started meets the condition. By adopting the technical scheme, the judgment condition is further refined, the accuracy of the system is improved, and the system is prevented from being misreported.
Preferably, the operation data further includes operating condition parameters, and the operating condition parameters are divided into cooling parameters and heating parameters.
Defining the pressure parameter of the pipe body at the exhaust end after the compressor is started as GUAN;
when the working condition parameter is refrigeration, judging whether the pressure parameter GUAN of the exhaust end pipe after the compressor is started meets the condition that GUAN is less than or equal to 240Kpa, and when the pressure parameter GUAN of the exhaust end pipe after the compressor is started meets the condition, judging that the pressure parameter GUAN of the exhaust end pipe after the compressor is started is abnormal; or judging whether the suction low pressure HD meets the HD less than or equal to 240Kpa after the compressor is started, and judging that the suction low pressure HD is abnormal after the compressor is started when the suction low pressure HD meets the condition after the compressor is started.
When the working condition parameter is heating, judging whether the pipe pressure parameter GUAN of the exhaust end after the compressor is started meets the GUAN which is less than or equal to 120Kpa, and when the pipe pressure parameter GUAN of the exhaust end after the compressor is started meets the condition, judging that the pipe pressure parameter GUAN of the exhaust end after the compressor is started is abnormal; or judging whether the suction low pressure HD after the compressor is started meets the HD less than or equal to 120Kpa or not, and judging that the suction low pressure HD after the compressor is started is abnormal when the suction low pressure HD after the compressor is started meets the condition, wherein the unit Kpa represents kilopascal.
Under the refrigeration working condition or the heating condition, any one of the pressure parameter GUAN of the exhaust end pipe after the compressor is started and the suction low pressure HD after the compressor is started is selected correspondingly for judgment, and then the fault of the throttling element can be obtained only by matching with the load FU of the compressor, the absolute value WEN of the difference value of the water inlet temperature, the high pressure parameter GAO of the exhaust before the compressor is started and the suction low pressure QD before the compressor is started.
By adopting the technical scheme, the fault point can be accurately positioned through comparison of multiple data, the judgment precision of the fault prediction model is improved, and system misjudgment is avoided.
Preferably, the operation data is preprocessed, and the preprocessing includes: and eliminating at least one of abnormal data, making up data loss and judging peak value.
And the storage server acquires the operation data acquired by the acquisition server and preprocesses the operation data. Wherein the pretreatment comprises: eliminating abnormal data, making up for data loss, judging peak value and the like. In the application, the abnormal data elimination refers to the direct elimination of the disordered data which obviously exceeds the normal range and appears in the data, the adopted means is conventional logic comparison, and the abnormal data is directly eliminated, for example, when the operating power of the air conditioner compressor is 200%, the data is directly judged to be disordered and directly deleted. The data missing means that the acquired data is less than the preset data quantity in unit time, the data is judged to be missing, when the situation occurs, an interpolation method in the prior art is adopted, the intermediate data is predicted by acquiring the data change dynamic state of two ends or one end of the missing data, the intermediate data is generated and is correspondingly supplemented, and by adopting the method, the accuracy of the data is improved, and the system is prevented from being misjudged. The peak value judgment means that abnormal peak or trough data in the acquired data is judged, the mean value X and the variance Y of the parameter in unit time are calculated aiming at the peak value judgment, and when the abnormal value is larger than X + 3X Y, the value is judged to be invalid and is eliminated. By adopting the method, the interference of abnormal wave crest or wave trough data on the fault prediction model is avoided, and the misjudgment of the system is avoided.
Preferably, the making up for the data loss includes: at least one of mean interpolation, maximum likelihood estimation, and multiple interpolation.
The attributes of the operational data are classified into fixed-distance type and non-fixed-distance type. If the missing value of the operation data is of a fixed distance type, interpolating the missing value by using the average value of the attribute existing values; if the missing value of the operation data is of a non-fixed distance type, the missing value is filled by the mode (namely the value with the highest occurrence frequency) of the attribute according to the mode principle in statistics.
Under the condition that the deletion type is random deletion, assuming that the model is correct for a complete sample, maximum likelihood estimation can be carried out on the unknown parameters by observing the marginal distribution of data.
The multiple interpolation estimates the value to be interpolated, then adds different data noises to form multiple groups of selectable interpolation values. And selecting the most appropriate interpolation value according to the variation trend of the data average value. Under the condition of data loss, different data loss compensation methods are adopted according to different data types, so that the accuracy of data is improved, and the misjudgment of a fault prediction model is avoided.
Preferably, a Kafka system and a Flume system are arranged in a transmission link between the data acquisition module and the data storage module.
Where Kafka refers to a middleware that a specialized tool is designed to send data to the HDFS. The flash is a distributed system for collecting, aggregating and transmitting mass logs. The Kafka and the Flume are mutually matched to ensure zero data loss and avoid the interference of data loss on the fault prediction model, so that the accuracy of fault early warning of the fault prediction model is improved.
Preferably, the sample data of the fault prediction model includes experimental data and/or historical operating data obtained after judgment of the associated fault under the laboratory condition.
After the model is built, the model is trained through sample data obtained after the correlation fault judgment under the laboratory condition to ensure that the fault prediction model has basic judgment capability, then the fault prediction model is trained through the sample data collected historically to further optimize the judgment capability of the fault prediction model, and the model is trained while continuously obtaining new sample data, namely, the fault diagnosis is carried out, so that the accuracy of model prediction is gradually improved.
Through the scheme, data comparison is not required to be carried out by designers one by one, and the working efficiency of workers is greatly improved. The consumption of human resources is reduced, and the time for solving the fault is shortened.
The invention further provides an air conditioner which comprises a controller and the throttling element, wherein the controller carries out early warning data processing on the fault of the throttling element according to any one of the air conditioner throttling element fault early warning methods in the embodiments.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents of the present invention, which are made by the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A fault early warning method for an air conditioner throttling element is characterized by obtaining operation data in a period of time before the fault of the air conditioner, correspondingly marking the operation state of the throttling element on the operation data, and generating sample data;
constructing a model according to the sample data, and generating a fault prediction model;
and acquiring the operating data of the air conditioner in real time, and predicting whether the air conditioner throttling element fails or not through the fault prediction model.
2. The method for early warning of the fault of the air conditioner throttling component as claimed in claim 1, wherein the operation data in a period of time before the fault or the operation data of the air conditioner at least comprises: and the time interval is the compressor load corresponding to the time interval, the absolute value of the difference value of the water outlet temperature and the water inlet temperature, the exhaust pressure before the compressor is started, the suction pressure before the compressor is started, and the suction pressure after the compressor is started or the pressure of a pipe body at the exhaust end after the compressor is started.
3. The air conditioner throttling element fault early warning method as claimed in claim 1, wherein the fault prediction model is constructed by adopting an LSTM algorithm.
4. The air conditioner throttling component fault early warning method as claimed in claim 3, wherein the generating of the fault prediction model specifically comprises:
if the state mark of the throttling element is normal, inputting the preprocessed sample data corresponding to the state mark to a forgetting gate of an LSTM algorithm; if the state mark of the throttling element is a fault, inputting the preprocessed sample data corresponding to the state mark to an input gate of the LSTM algorithm to obtain an output gate of the LSTM algorithm; and
and repeating the previous judging step until all sample data are input, and obtaining a fault prediction model.
5. The method for early warning the fault of the air conditioner throttling element as claimed in claim 1, wherein the step of correspondingly marking the operating state of the throttling element on the operating data specifically comprises the steps of: setting a numerical range of operation data in a period of time before the air conditioner fails when the state of the throttling element is in a fault state; and comparing the operation data in a period of time before the air conditioner fault with a set numerical range, and marking the state of the throttling element as a fault when the operation data in the period of time before the air conditioner fault falls into the numerical range when the state is the fault.
6. The method for early warning the fault of the throttling element of the air conditioner as claimed in claim 5, wherein the operation data further comprises working condition parameters, and the working condition parameters are divided into refrigeration parameters and heating parameters.
7. The air conditioner throttling component fault early warning method as claimed in claim 1, wherein the operation data is preprocessed, and the preprocessing comprises: and eliminating at least one of abnormal data, making up data loss and judging peak value.
8. The air conditioner throttling element fault early warning method of claim 7, wherein the making up for the data loss comprises: at least one of mean interpolation, maximum likelihood estimation, and multiple interpolation.
9. The method for early warning of the fault of the air conditioner throttling component as claimed in claim 1, wherein the sample data of the fault prediction model comprises experimental data and/or historical operating data obtained after judgment of the associated fault under laboratory conditions.
10. An air conditioner, comprising a controller and a throttling component, wherein the controller carries out early warning data processing on the fault of the throttling component according to the air conditioner throttling component fault early warning method as claimed in claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010647406.4A CN111765593B (en) | 2020-07-07 | 2020-07-07 | Air conditioner throttling component fault early warning method and air conditioner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010647406.4A CN111765593B (en) | 2020-07-07 | 2020-07-07 | Air conditioner throttling component fault early warning method and air conditioner |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111765593A true CN111765593A (en) | 2020-10-13 |
| CN111765593B CN111765593B (en) | 2021-11-12 |
Family
ID=72724803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010647406.4A Active CN111765593B (en) | 2020-07-07 | 2020-07-07 | Air conditioner throttling component fault early warning method and air conditioner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111765593B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113687966A (en) * | 2021-10-26 | 2021-11-23 | 印象(山东)大数据有限公司 | Monitoring method and device based on electronic equipment and electronic equipment |
| CN114817865A (en) * | 2022-06-28 | 2022-07-29 | 深圳市傲立电子有限公司 | Big data-based operation fault prediction system for radio frequency power amplifier |
| CN114923261A (en) * | 2022-05-05 | 2022-08-19 | 青岛海信日立空调系统有限公司 | Central air conditioning unit fault monitoring method and system and central air conditioning unit |
| CN115127192A (en) * | 2022-05-20 | 2022-09-30 | 中南大学 | Semi-supervised water chilling unit fault diagnosis method and system based on graph neural network |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106500238A (en) * | 2016-09-12 | 2017-03-15 | 珠海格力电器股份有限公司 | Electric expansion valve fault detection method, device and multi-connected machine device systems |
| CN108613335A (en) * | 2018-03-12 | 2018-10-02 | 珠海格力电器股份有限公司 | Fault detection method, device, storage medium and the processor of air-conditioning |
| CN109708249A (en) * | 2018-12-29 | 2019-05-03 | 珠海格力电器股份有限公司 | Air-conditioning component failure prediction method, device and computer equipment |
| CN109738776A (en) * | 2019-01-02 | 2019-05-10 | 华南理工大学 | Fan converter open-circuit fault recognition methods based on LSTM |
| CN110414666A (en) * | 2019-05-28 | 2019-11-05 | 河海大学 | Pumping plant unit fault recognition method based on improved LSTM network |
| CN110500825A (en) * | 2019-09-24 | 2019-11-26 | 珠海格力电器股份有限公司 | Electric expansion valve method for diagnosing faults and device, air-conditioning and storage medium |
| KR20200022948A (en) * | 2018-08-24 | 2020-03-04 | 포항공과대학교 산학협력단 | Method for diagnosing and predicting robot arm's failure |
| WO2020115935A1 (en) * | 2018-12-06 | 2020-06-11 | 三菱電機株式会社 | Air conditioning system |
-
2020
- 2020-07-07 CN CN202010647406.4A patent/CN111765593B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106500238A (en) * | 2016-09-12 | 2017-03-15 | 珠海格力电器股份有限公司 | Electric expansion valve fault detection method, device and multi-connected machine device systems |
| CN108613335A (en) * | 2018-03-12 | 2018-10-02 | 珠海格力电器股份有限公司 | Fault detection method, device, storage medium and the processor of air-conditioning |
| KR20200022948A (en) * | 2018-08-24 | 2020-03-04 | 포항공과대학교 산학협력단 | Method for diagnosing and predicting robot arm's failure |
| WO2020115935A1 (en) * | 2018-12-06 | 2020-06-11 | 三菱電機株式会社 | Air conditioning system |
| CN109708249A (en) * | 2018-12-29 | 2019-05-03 | 珠海格力电器股份有限公司 | Air-conditioning component failure prediction method, device and computer equipment |
| CN109738776A (en) * | 2019-01-02 | 2019-05-10 | 华南理工大学 | Fan converter open-circuit fault recognition methods based on LSTM |
| CN110414666A (en) * | 2019-05-28 | 2019-11-05 | 河海大学 | Pumping plant unit fault recognition method based on improved LSTM network |
| CN110500825A (en) * | 2019-09-24 | 2019-11-26 | 珠海格力电器股份有限公司 | Electric expansion valve method for diagnosing faults and device, air-conditioning and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 周奇才: "基于LSTM循环神经网络的盾构机故障预测系统设计", 《现代制造、工艺装备》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113687966A (en) * | 2021-10-26 | 2021-11-23 | 印象(山东)大数据有限公司 | Monitoring method and device based on electronic equipment and electronic equipment |
| CN114923261A (en) * | 2022-05-05 | 2022-08-19 | 青岛海信日立空调系统有限公司 | Central air conditioning unit fault monitoring method and system and central air conditioning unit |
| CN114923261B (en) * | 2022-05-05 | 2023-07-18 | 青岛海信日立空调系统有限公司 | Central air conditioner unit fault monitoring method and system and central air conditioner unit |
| CN115127192A (en) * | 2022-05-20 | 2022-09-30 | 中南大学 | Semi-supervised water chilling unit fault diagnosis method and system based on graph neural network |
| CN115127192B (en) * | 2022-05-20 | 2024-01-23 | 中南大学 | Semi-supervised water chilling unit fault diagnosis method and system based on graph neural network |
| CN114817865A (en) * | 2022-06-28 | 2022-07-29 | 深圳市傲立电子有限公司 | Big data-based operation fault prediction system for radio frequency power amplifier |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111765593B (en) | 2021-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111765593B (en) | Air conditioner throttling component fault early warning method and air conditioner | |
| CN110425694B (en) | High-speed rail intelligent station heating ventilation air conditioner energy efficiency control management method based on PHM | |
| CN109595763A (en) | The control strategy optimization method, apparatus and computer equipment of air-conditioning system | |
| CN114801751B (en) | Automobile battery fault prediction system based on data analysis | |
| CN110672332B (en) | Gas turbine fault early warning system based on SARIMA model | |
| CN107144085B (en) | A kind of method, apparatus and system of determining breakdown of refrigerator | |
| US20240010100A1 (en) | Processing of status data of a battery for aging estimation | |
| US9733630B2 (en) | Interactive energy device for environmental stewardship | |
| CN110676845B (en) | Load adjusting method, device and system and storage medium | |
| CN104049606A (en) | Remote multi-dimensional household appliance information management system and management method thereof | |
| CN111897771A (en) | Gas meter message testing method and system based on intelligent analysis model | |
| US20210207829A1 (en) | Air conditioning management system and communication control device | |
| CN117319179A (en) | Equipment abnormality monitoring method and system based on mechanism model and industrial Internet of things | |
| CN116207766B (en) | Dynamic threshold control method and system for lithium battery energy storage system | |
| CN117096983A (en) | Battery monitoring and management system and method thereof | |
| CN111929579A (en) | Generator online fault diagnosis method and device and computer device | |
| CN115127194B (en) | Method, equipment and medium for detecting faults of central air conditioner water chilling unit | |
| CN110568257A (en) | continuous monitoring method and device for energy consumption of air conditioner | |
| CN114427742B (en) | Central air-conditioning cold station energy efficiency control method, device, equipment and storage medium | |
| CN115480556A (en) | Intelligent online fault diagnosis system for heating and ventilation electromechanical equipment | |
| CN105354232B (en) | A kind of air conditioner energy saving diagnostic system and air conditioner energy saving diagnostic method based on ontology | |
| CN105223917B (en) | A kind of complex control system and method based on different type compressed air unit | |
| KR102451876B1 (en) | Server and method for providing management information of vehicle | |
| CN108876078B (en) | Method for calculating energy consumption system performance improvement strategy and energy consumption system monitoring device | |
| KR102466132B1 (en) | The service system and method for battery management system of electric vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |